ClawHub
Back to skill

Security audit

Intercom GenAIgrp

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, transparent inter-agent messaging helper that should be used carefully but does not show hidden, destructive, or deceptive behavior.

Install only if you want agents to send explicit, user-triggered messages to other OpenClaw sessions. Verify the target session before sending, do not include secrets unless the recipient is trusted and opt-in, and prefer a version with declared tool scope and clearer target validation if available.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The skill claims to perform restricted inter-agent message routing via !target syntax, but the file only provides natural-language instructions and no verifiable implementation or enforcement. That mismatch can mislead operators or downstream agents into manually carrying out message forwarding without proper validation, authorization checks, or platform controls, creating a confused-deputy channel for unintended data sharing or impersonated coordination.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.